Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation
For practitioners deploying LVLMs, TLVS offers a lightweight, plug-and-play method to reduce hallucinations without retraining, though it is an incremental improvement over existing activation steering approaches.
TLVS mitigates hallucinations in LVLMs by applying token-level, visual-sensitivity-adaptive steering only to critical decoding steps, achieving consistent improvements over prior steering methods across multiple benchmarks (e.g., POPE, AMBER, CHAIR, MMHal, HallusionBench).
Large vision language models (LVLMs) have made rapid advancements and are deployed across various applications, yet hallucinations remain a major challenge. Activation steering is appealing due to its minimal training overhead and controllability at inference time. However, we found that during autoregressive decoding, visual conditioning affects token prediction sparsely and locally across decoding steps, and many existing methods that average image-versus-no-image differences over the entire sequence dilute these critical signals, yielding low signal-to-noise ratio steering directions. Additionally, many existing methods apply a fixed steering strength, which misallocates the intervention budget, over-perturbs non-critical tokens, and can cause instability. To address these limitations, we propose Token-Level Visual-Sensitivity Steering (TLVS) for hallucination mitigation. Our approach first extracts token-level steering vectors and refines them, and then applies fine-grained, visual-sensitivity-adaptive steering only where it matters. This lightweight, plug-and-play mechanism requires only minimal training for calibration and can be applied across diverse vision-language models. It modulates the steering strength at each decoding step, selectively suppressing hallucination-prone spans while preserving evidence-grounded content. We evaluate TLVS on several benchmarks, including POPE, AMBER, CHAIR (COCO), MMHal, and HallusionBench, demonstrating consistent improvements over previous steering methods.